---
library_name: peft
license: mit
base_model: zai-org/GLM-OCR
tags:
- base_model:adapter:zai-org/GLM-OCR
- llama-factory
- lora
- transformers
metrics:
- accuracy
pipeline_tag: text-generation
model-index:
- name: smoke_test_glm4v_checkpoints
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# smoke_test_glm4v_checkpoints

This model is a fine-tuned version of [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) on the gujarati_ocr_stream dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5668
- Accuracy: 0.5594

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1
- training_steps: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 2.7841        | 0.6154 | 2    | 2.7496          | 0.5348   |
| 2.6433        | 1.0    | 4    | 2.5868          | 0.5556   |


### Framework versions

- PEFT 0.18.1
- Transformers 5.2.0
- Pytorch 2.11.0+cu130
- Datasets 4.0.0
- Tokenizers 0.22.2